Multi-Edge Task Scheduling for TDMA Offloading Bottlenecks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing multi-edge device assisted edge computing networks face challenges in optimizing offloading selections and scheduling order of computation tasks to minimize maximum task completion time for computation-constrained wireless devices.
Innovation Solution
A task scheduling method is employed in a TDMA communication mode, deciding offloading selections and scheduling order based on workload, transmission rates, and computation rates to minimize maximum task completion time, involving steps to acquire and initialize a scheduling policy, decide offloading selections, and offload tasks sequentially.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If multiple edge devices are deployed to accelerate task computation, then computation speed is improved, but task scheduling complexity increases
Solution Approach 1:
The patent segments the task scheduling problem into two distinct phases: (1) determining offloading selections for each wireless device to edge devices, and (2) determining the execution order of tasks at edge devices. This segmentation allows each phase to be optimized independently, reducing overall scheduling complexity while maintaining high computation speed through multi-edge device deployment.
Solution Approach 2:
The patent performs preliminary actions by first determining all offloading selections before determining the execution order. The offloading selection phase prepares the foundation by identifying which wireless devices offload to which edge devices, allowing the subsequent execution order phase to focus solely on sequencing tasks efficiently across the already-determined device assignments.
2Productivity
If wireless devices offload tasks to edge devices, then computation capability is improved, but transmission time is increased
Solution Approach 1:
The patent changes key parameters including transmission rates between wireless devices and edge devices, computation rates of edge devices, and workload characteristics. By optimizing the scheduling policy based on these parameters, the system minimizes total task completion time while utilizing the enhanced computation capability of edge devices, effectively balancing transmission overhead against computation gains.
Data Source
AI summary
A task scheduling method for a multi-edge device assisted edge computing network, includes: step 1: acquiring the workloads of computation tasks to be processed by the wireless devices, the transmission rates between the wireless devices and edge devices and the computation rates of the edge devices, and initializing a scheduling policy S as an empty array; step 2: successively deciding offloading selections of the wireless devices according to the serial numbers of the wireless devices, and inserting the offloading selections into appropriate inserting positions in the scheduling policy S; and, step 3: offloading the computation tasks, according to the final scheduling policy S and by the wireless devices, to the designated edge devices for computation. The present invention is suitable for, in a time division multiple access (TDMA) communication mode and a binary offloading mode.